Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 580 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0386. Min Range: -2.0386

Max Act: 2.0386. Min Act: -0.0000

Data Index: 420321 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.7166. Min Act: -0.0000

Data Index: 672698 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1290429 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.5062. Min Act: -0.0000

Data Index: 489954 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.5742. Min Act: -0.0000

Data Index: 778261 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.5625. Min Act: -0.0000

Data Index: 64102 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.4421. Min Act: -0.0000

Data Index: 1318566 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1133918 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.5495. Min Act: -0.0000

Data Index: 126256 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1185812 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.5119. Min Act: -0.0000

Data Index: 149732 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.4214. Min Act: -0.0000

Data Index: 46180 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.3159. Min Act: -0.0000

Data Index: 493438 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.2276. Min Act: -0.0000

Data Index: 683761 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.3075. Min Act: -0.0000

Data Index: 62028 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.3021. Min Act: -0.0000

Data Index: 951018 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1154447 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.2625. Min Act: -0.0000

Data Index: 222449 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.2002. Min Act: -0.0000

Data Index: 749966 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.2695. Min Act: -0.0000

Data Index: 875781 (C4 (Web Text))

Max Activating Token Index: 897